English
Related papers

Related papers: Convergence and sample complexity of gradient meth…

200 papers

In this paper, we present a novel sufficient condition for the stability of discrete-time linear systems that can be represented as a set of piecewise linear constraints, which make them suitable for quadratic programming optimization…

Systems and Control · Electrical Eng. & Systems 2024-04-25 Marc Mitjans , Liangting Wu , Roberto Tron

We study the global linear convergence of policy gradient (PG) methods for finite-horizon continuous-time exploratory linear-quadratic control (LQC) problems. The setting includes stochastic LQC problems with indefinite costs and allows…

Optimization and Control · Mathematics 2024-03-05 Michael Giegrich , Christoph Reisinger , Yufei Zhang

We consider derivative-free algorithms for stochastic and non-stochastic convex optimization problems that use only function values rather than gradients. Focusing on non-asymptotic bounds on convergence rates, we show that if pairs of…

Optimization and Control · Mathematics 2014-08-21 John C. Duchi , Michael I. Jordan , Martin J. Wainwright , Andre Wibisono

Distributionally robust optimization (DRO) problems are increasingly seen as a viable method to train machine learning models for improved model generalization. These min-max formulations, however, are more difficult to solve. We therefore…

Machine Learning · Statistics 2020-11-03 Soumyadip Ghosh , Mark Squillante , Ebisa Wollega

Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several…

The article introduces a method to learn dynamical systems that are governed by Euler--Lagrange equations from data. The method is based on Gaussian process regression and identifies continuous or discrete Lagrangians and is, therefore,…

Numerical Analysis · Mathematics 2025-07-01 Christian Offen

In reinforcement learning (RL), offline learning decoupled learning from data collection and is useful in dealing with exploration-exploitation tradeoff and enables data reuse in many applications. In this work, we study two offline…

Machine Learning · Computer Science 2022-02-08 Jing Dong , Xin T. Tong

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice…

Optimization and Control · Mathematics 2021-02-19 Xiaoyu Wang , Sindri Magnússon , Mikael Johansson

The neural ordinary differential equation (ODE) framework has emerged as a powerful tool for developing accelerated surrogate models of complex physical systems governed by partial differential equations (PDEs). A popular approach for PDE…

Fluid Dynamics · Physics 2025-03-26 Ashish S. Nair , Shivam Barwey , Pinaki Pal , Jonathan F. MacArt , Troy Arcomano , Romit Maulik

Iterative optimization algorithms depend on access to information about the objective function. In a differentiable programming framework, this information, such as gradients, can be automatically derived from the computational graph. We…

Optimization and Control · Mathematics 2025-07-08 Vincent Roulet , Siddhartha Srinivasa , Maryam Fazel , Zaid Harchaoui

This review presents modern gradient-free methods to solve convex optimization problems. By gradient-free methods, we mean those that use only (noisy) realizations of the objective value. We are motivated by various applications where…

We study the problem of high-dimensional robust mean estimation in the presence of a constant fraction of adversarial outliers. A recent line of work has provided sophisticated polynomial-time algorithms for this problem with…

Machine Learning · Computer Science 2020-05-05 Yu Cheng , Ilias Diakonikolas , Rong Ge , Mahdi Soltanolkotabi

In this paper we study model reduction of linear and bilinear quadratic stochastic control problems with parameter uncertainties. Specifically, we consider slow-fast systems with unknown diffusion coefficient and study the convergence of…

Optimization and Control · Mathematics 2021-02-10 Hafida Bouanani , Carsten Hartmann , Omar Kebiri

The GRadient Ascent Pulse Engineering (GRAPE) method is widely used for optimization in quantum control. GRAPE is gradient search method based on exact expressions for gradient of the control objective. It has been applied to coherently…

Quantum Physics · Physics 2023-07-18 Vadim Petruhanov , Alexander Pechen

Recent studies have shown that many nonconvex machine learning problems satisfy a generalized-smooth condition that extends beyond traditional smooth nonconvex optimization. However, the existing algorithms are not fully adapted to such…

Optimization and Control · Mathematics 2025-10-03 Yufeng Yang , Erin Tripp , Yifan Sun , Shaofeng Zou , Yi Zhou

How can we understand gradient-based training over non-convex landscapes? The edge of stability phenomenon, introduced in Cohen et al. (2021), indicates that the answer is not so simple: namely, gradient descent (GD) with large step sizes…

Machine Learning · Computer Science 2026-02-03 Eric Regis , Sinho Chewi

Many machine learning solutions are framed as optimization problems which rely on good hyperparameters. Algorithms for tuning these hyperparameters usually assume access to exact solutions to the underlying learning problem, which is…

Machine Learning · Computer Science 2020-11-09 Matthias J. Ehrhardt , Lindon Roberts

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Machine Learning · Computer Science 2018-07-11 Chi Jin , Zeyuan Allen-Zhu , Sebastien Bubeck , Michael I. Jordan

We propose two policy gradient algorithms for solving the problem of control in an off-policy reinforcement learning (RL) context. Both algorithms incorporate a smoothed functional (SF) based gradient estimation scheme. The first algorithm…

Machine Learning · Computer Science 2024-06-25 Nithia Vijayan , Prashanth L. A

In this paper, we study the global convergence of model-based and model-free policy gradient descent and natural policy gradient descent algorithms for linear quadratic deep structured teams. In such systems, agents are partitioned into a…

Multiagent Systems · Computer Science 2020-12-16 Vida Fathi , Jalal Arabneydi , Amir G. Aghdam